INDEX
Explanations
references to a specific company or brand
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.06
0.2%
1343
+0.06
0.2%
832
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1343
+0.06
0.17
283
+0.06
0.05
1871
+0.05
0.04
Negative Logits
<bos>
-1.72
-0.91
ⓧ
-0.86
/**
-0.85
<?
-0.84
mustered
-0.71
plundered
-0.68
overthrown
-0.68
rejoined
-0.67
overtook
-0.67
POSITIVE LOGITS
bayern
1.41
franz
1.41
maroc
1.41
gmbh
1.39
meis
1.36
wien
1.32
italia
1.27
baum
1.27
riva
1.26
lele
1.25
Activations Density 1.133%